© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33245
    Prev
    Next
    INDEX
    Explanations

    processes or actions of a certain kind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ones
    -0.10
    å¼ı
    -0.10
    oron
    -0.09
     Sized
    -0.09
     Hawkins
    -0.09
    onation
    -0.08
    izr
    -0.08
    -fashion
    -0.08
    atif
    -0.08
    -esque
    -0.08
    POSITIVE LOGITS
     duration
    0.11
     experience
    0.11
     environment
    0.10
    spa
    0.10
     plan
    0.10
     philosoph
    0.10
     locations
    0.10
     requis
    0.10
     pace
    0.10
    hib
    0.10
    Activations Density 1.424%

    No Known Activations